community pool / model answer
GLM-5.3-Flash-GGUF
chat · unsloth/GLM-5.3-Flash-GGUF
22.6 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Radeon AI Pro R9700 32GB | 1-bit | 17.4 tok/s | reported | 732 | 92.2 GB | 32,768 | llama.cpp |
| Radeon AI Pro R9700 32GB | 2-bit | 16.6 tok/s | reported | 786 | 101.9 GB | 32,768 | llama.cpp |
| RTX 3090 24GB ×8 | 4-bit | 35 tok/s | reported | 2,167 | 166.8 GB | 204,800 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.